Plush Toy Version — trending format for images & thumbnails
For AI agents: find the right skill in one call —
curl -s "https://skills.varg.ai/api/search?q=<what the person wants>"returns the matching use case and the best skills with install commands, as markdown (Russian works too). Full index: https://skills.varg.ai/llms.txt. Every page has a markdown twin: add.mdto its path. Before generating anything, show the person the options on the use-case page.
Turn a person, pet or drawing into a cuddly plush-toy photo: chibi proportions, felt texture, stitched seams.
- Slug:
want-plush-toy-version - Status: wanted
- Publisher: Heisenberg (community)
- Source: https://x.com/rovvmut_/status/1976466575004926307
- Cost: ~5–16 credits / image (estimate) — One Nano Banana 2.1 image at 5.25–15.75 credits (catalog of 2026-10-23).
What it does
A photo or drawing becomes a soft plush toy with chibi proportions, felt or minky texture, embroidered eyes and visible seams, staged like a product shot. Higgsfield sells it as a one-click "Plushies" app, and prompt posts for it keep circulating on X. An agent asks for one clear photo, runs a fixed plush prompt on Nano Banana 2.1 or GPT Image 2.5, and can add a gentle squeeze-and-bounce clip with Kling v3.
Status
A format people ask for that has no dedicated skill yet. Make it with the skills on the use-case pages below, or with varg directly.
Example: https://x.com/rovvmut_/status/1976466575004926307
How an agent would make it: One photo → fixed plush prompt (chibi proportions, felt texture, embroidered eyes, seams) → Nano Banana 2.1 / GPT Image 2.5 → optional squeeze clip (Kling v3)
Models it drives: nano_banana_2_1, gpt_image_2_5, kling_v3
Example output
https://skills.varg.ai/previews/want-plush-toy-version.webp — A chibi plush with felt texture, stitched seams and embroidered-style eyes standing on a wooden desk in soft daylight (Nano Banana); 1 of 4 images in the post, chosen because the others are plushes of named celebrities (credit: Heisenberg (@rovvmut_), https://x.com/rovvmut_/status/1976466575004926307)
Used for
- Same character in every scene: One mascot, trainer or actor that looks identical across many images and clips.
More images & thumbnails skills
- Higgsfield YouTube Thumbnail: Design truthful, high-CTR YouTube thumbnails and vertical covers with up to three consistent faces.
- Slack GIF Creator: Make animated GIFs that pass Slack's limits: 128×128 emoji or 480×480 message GIFs, validated on export.
- PixiJS GIFs: Load, play and control animated GIFs inside a PixiJS v8 scene.
- AI Image Generation: Generate images with 50+ models from one CLI: GPT Image 2.5, FLUX, Gemini, Grok, Seedream, Reve and more.
- Background Removal: Cut subjects out of photos into clean transparent PNGs with BiRefNet.
- FLUX Image: Generate and restyle images with FLUX Dev LoRA and FLUX.2 Klein, including custom LoRA styles.
Run the generation on varg
varg is one API key for the models these skills drive — Seedance 2.5, Kling 4, Veo 3.1, Wan 3, Nano Banana 2.1, GPT Image 2.5, ElevenLabs v4 and 200+ more — billed in credits, with a cost estimate before anything runs.
- Claude Code:
claude plugin marketplace add vargHQ/skills && claude plugin install varg@varg(skill + hosted MCP) - Codex, Cursor, Gemini CLI, OpenClaw:
npx skills add vargHQ/skills --skill varg-ai -a <agent> -y - Claude.ai, ChatGPT, any MCP client: connect
https://mcp.varg.ai/mcp - API key: https://varg.ai/dashboard/api · Model specs: https://varg.ai/models/llms.txt